Role Overview
Design, develop, and maintain scalable Gen AI applications using LLMs, RAG, and agent-based architectures. This role involves building end-to-end AI solutions, from RAG pipelines to intelligent AI agents, ensuring they are production-ready, secure, and scalable.
Responsibilities
- Design, develop, and maintain scalable Gen AI applications using LLMs, RAG, and agent-based architectures.
- Develop and optimize backend APIs and microservices using Python and relevant frameworks.
- Build end-to-end RAG pipelines, including document ingestion, preprocessing, chunking, embeddings, retrieval, and indexing.
- Work with vector databases for efficient semantic search and context retrieval.
- Develop LLM applications using LangChain, LangGraph, and LangFuse.
- Implement and deploy LLM solutions using Amazon Bedrock and integrate foundation models into enterprise applications.
- Design intelligent AI agents, including tool calling, workflow orchestration, memory, and multi-step reasoning patterns.
- Develop effective system prompts and context-engineering strategies to improve accuracy, relevance, and reliability of Gen AI applications.
- Implement SSO-based authentication and authorization for enterprise Gen AI applications.
- Containerize applications and services using Docker and support scalable deployment across enterprise environments.
- Implement observability and monitoring for APIs, LLM applications, model performance, latency, failures, and usage.
- Optimize applications for performance, scalability, reliability, security, and cost efficiency.
- Collaborate with architects, data engineers, product teams, and business stakeholders to translate requirements into production-ready AI solutions.
- Follow best practices for Gen AI security, data privacy, prompt management, evaluation, and responsible AI.
- Troubleshoot production issues and continuously enhance the quality and performance of deployed Gen AI applications.
Requirements
- Proven experience in building and deploying Gen AI and LLM based applications.
- Strong proficiency in Python and backend development.
- Experience with RAG architectures and vector databases.
- Hands-on experience with LangChain or similar orchestration frameworks.
- Familiarity with cloud-based AI services like Amazon Bedrock.
- Knowledge of containerization using Docker.
Skills
- Python
- LangChain
- Amazon Bedrock
- Docker
- Vector Databases